PaperHub
影响力指数
74.81/100
前 1.9%
全站排名 #1,227
发表论文31 篇
平均评分4.9
年均产出10.3 篇/年

Wenzhao Zheng

Postdoc@University of California, Berkeley·美国·OpenReview
研究方向

autonomous driving · explainable AI · deep representation learning · deep metric learning

7.0
16

S2GO: Streaming Sparse Gaussian Occupancy

ICLR 2026Poster
6.5
19

Streaming Visual Geometry Transformer

ICLR 2026Poster
二作
6.5
14

Latent Diffusion Model without Variational Autoencoder

ICLR 2026Poster
三作
5.3
15

DiffMoE: Dynamic Token Selection for Scalable Diffusion Transformers

ICLR 2026Rejected
5.0
18

Underwater Visual Geometry Estimation with Self-supervised Prototype-Graph Modulation

ICLR 2026Rejected
二作
5.0
14

Astra: General Interactive World Model with Autoregressive Denoising

ICLR 2026Poster
三作
4.5
5

MoRe4D: Joint 3D Motion Generation and Geometry Reconstruction for 4D Synthesis from a Single Image

ICLR 2026Withdrawn
三作
4.0
5

Lightning Video: Building Compact Diffusion Transformers for High-Fidelity On-Device Video Generation

ICLR 2026Withdrawn
3.5
5

Quantize-then-Rectify: Accelerating VQ-VAE Training in Latent Feature Space

ICLR 2026Withdrawn
三作
3.5
10

Terra: Explorable Native 3D World Model with Point Latents

ICLR 2026Withdrawn
三作
3.5
6

Moaw: Unleashing Motion Awareness for Video Diffusion Models

ICLR 2026Rejected
三作
3.5
5

NeXT-IMDL: Build Benchmark for NeXT-Generation Image Manipulation Detection & Localization

ICLR 2026Withdrawn
3.3
4

READ: End-to-End Autonomous Driving Made Safer with Efficient Reinforcement Learning

ICLR 2026Withdrawn
三作
3.3
4

ManiCoG: Training-Free Improvement for GUI Grounding via Manipulation Chains

ICLR 2026Withdrawn
3.3
4

SaLon3R: Structure-aware Long-term Generalizable 3D Reconstruction from Unposed Images

ICLR 2026Withdrawn
3.0
5

OGGSplat: Open-Vocabulary Gaussian Growing for Expanded Field-of-View

ICLR 2026Withdrawn
三作
2.5
5

End-to-End Unified Dense 3D Geometry and Motion Perception

ICLR 2026Withdrawn
二作
2.5
11

MoCtrl4D: Precise and Efficient Motion-Guided 4D Content Generation

ICLR 2026Rejected
三作
6.8
42

Point3R: Streaming 3D Reconstruction with Explicit Spatial Pointer Memory

NeurIPS 2025Poster
二作
6.5
19

UniDrive: Towards Universal Driving Perception Across Camera Configurations

ICLR 2025Poster
二作
6.4
37

QuadricFormer: Scene as Superquadrics for 3D Semantic Occupancy Prediction

NeurIPS 2025Poster
二作
6.0
17

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

NeurIPS 2025Poster
三作
5.5
23

V2M: Visual 2-Dimensional Mamba for Image Representation Learning

ICLR 2025Rejected
二作
5.5
22

PixelGaussian: Generalizable 3D Gaussian Reconstruction from Arbitrary Views

ICLR 2025Rejected
二作
5.5
13

SparseVLM: Visual Token Sparsification for Efficient Vision-Language Model Inference

ICML 2025Poster
5.4
15

OccSora: 4D Occupancy Generation Models as World Simulators for Autonomous Driving

ICLR 2025Rejected
二作
5.3
22

DrivingRecon: Large 4D Gaussian Reconstruction Model For Autonomous Driving

ICLR 2025Rejected
三作
5.2
44

SparseVLM: Visual Token Sparsification for Efficient Vision Language Models Inference

ICLR 2025Rejected
5.0
6

GlobalMamba: Global Image Serialization for Vision Mamba

ICLR 2025Withdrawn
二作
合作者 (20)